---
title: "A Structural-Analysis-Based Information Fusion for Multi-Modal Cross-View Geo-Localization"
authors:
  - "Xu Yan"
  - "Xiaoran Zhang"
  - "Ziwei Shi"
  - "Yu Zang"
  - "Weiquan Liu"
  - "Cheng Wang"
doi: "10.24963/ijcai.2026/218"
url: "https://ijcai.org/proceedings/2026/218"
pdf: "https://ijcai.org/proceedings/2026/0218.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "1956-1964"
track: "Main Track"
keywords:
  - "Computer Vision: Multimodal learning"
  - "Computer Vision: 3D computer vision"
---

# A Structural-Analysis-Based Information Fusion for Multi-Modal Cross-View Geo-Localization

Xu Yan, Xiaoran Zhang, Ziwei Shi, Yu Zang, Weiquan Liu, Cheng Wang

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 1956-1964. DOI: [10.24963/ijcai.2026/218](https://doi.org/10.24963/ijcai.2026/218)

## Abstract

Cross-view geo-localization (CVGL) aims at localizing a ground-level query by retrieving its corresponding match from a database of geo-tagged satellite images. Existing multi-modal CVGL methods lack a structured design in the fusion stage, limiting their ability to fully exploit the information from multiple modalities. To overcome this limitation, we propose a Structural-Analysis-Based fusion principle that guides the design of network architecture. Following this principle, we present Decoupled Query Fusion (DQF), a novel fusion module that decouples feature interactions through role-specific learnable queries. These learnable queries aggregate features into distinct slots. Specifically, modality-specific queries capture unique information from each modality, while cross-modal queries extract redundant and synergistic information between different modalities. To better discriminate positive samples at varying geographic distances, we further propose Geo-aware Circle Loss, which adaptively weights supervision signal based on the geographical distance between samples and anchors. Extensive experiments on large-scale benchmarks demonstrate that our method significantly outperforms state-of-the-art approaches. Comprehensive ablation studies further validate the effectiveness of each component. Our code and models will be made publicly available.